Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Few-Shot Learning With a Strong Teacher
Han-Jia Ye, Ming Lu, De‐Chuan Zhan, Wei‐Lun Chao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LastShot (NC) teacher supervision | ProtoNet · miniImageNet 1-shot | accuracy: 62.39 -> 64.16 | Improved |
| add LastShot (NC) | FEAT · miniImageNet 1-shot | accuracy: 66.78 -> 67.33 | Improved |
| add LastShot (LR) | MetaOptNet · miniImageNet 1-shot | accuracy: 63.21 -> 65.08 | Improved |
| add LastShot (NC) | FEAT · tieredImageNet 1-shot | accuracy: 71.13 -> 72.03 | Improved |
| add LastShot (LR) | FEAT · FC-100 1-shot | accuracy: 42.56 -> 44.08 | Improved |
| add LastShot (LR) | FEAT · miniImageNet 50-shot | accuracy: 87.83 -> 89.03 | Improved |
| use B-class base classifier as teacher (ablation) | FEAT · miniImageNet 1-shot | accuracy: 66.78 -> 66.89 | No clear effect |
| weaken student with Autoaug without LastShot (ablation) | FEAT · miniImageNet 1-shot | accuracy: 66.78 -> 65.22 | Hurt |
| enlarge teacher inputs instead of direct query (ablation) | FEAT + LastShot (NC) · miniImageNet 1-shot | accuracy: 66.97 -> 67.33 | Improved |
| ensemble with SimpleShot instead of LastShot (ablation) | FEAT · miniImageNet 5-shot | accuracy: 82.05 -> 81.76 | No clear effect |
| add LastShot (NC) over ensemble (ablation) | ProtoNet · miniImageNet 5-shot | accuracy: 81.10 -> 81.23 | Improved |
| increase lambda to 10 (ablation) | FEAT + LastShot (NC) · miniImageNet 50-shot | accuracy: 88.76 -> 87.34 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DeepEMD — DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers (CVPR 2020) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning (ICCV 2021 · similarity 0.93)
- Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples (ICLR 2020 · similarity 0.92)
- A Theoretical Analysis of the Number of Shots in Few-Shot Learning (ICLR 2020 · similarity 0.91)
- Rethinking Few-shot Image Classification: A Good Embedding is All You Need? (ECCV 2020 · similarity 0.91)
- Pushing the Limit of Fine-Tuning for Few-Shot Learning: Where Feature Reusing Meets Cross-Scale Attention (AAAI 2024 · similarity 0.90)
- Scaling Few-Shot Learning for the Open World (AAAI 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
